MetaPoint represents 2D coordinates as special tokens in visual generative models to enable precise spatial control using existing positional encodings without architectural modifications.
arXiv preprint arXiv:2501.01097 (2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
RefineAnything is a multimodal diffusion model using Focus-and-Refine crop-and-resize with blended paste-back to achieve high-fidelity local image refinement and near-perfect background preservation.
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
citing papers explorer
-
MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation
MetaPoint represents 2D coordinates as special tokens in visual generative models to enable precise spatial control using existing positional encodings without architectural modifications.
-
OneHOI: Unifying Human-Object Interaction Generation and Editing
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
-
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
RefineAnything is a multimodal diffusion model using Focus-and-Refine crop-and-resize with blended paste-back to achieve high-fidelity local image refinement and near-perfect background preservation.
-
Advancing Aesthetic Image Generation via Composition Transfer
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.